Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add IsaiaScope/ai --skill iso-issue-trackinggit clone --depth 1 https://github.com/IsaiaScope/aiWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/isaiascope/ai/iso-issue-tracking)<a href="https://agentmods.dev/skills/isaiascope/ai/iso-issue-tracking"><img src="https://agentmods.dev/badge/skills/isaiascope/ai/iso-issue-tracking.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00088 | $0.05185 |
| Opus 5 | $0.00044 | $0.02593 |
| Sonnet 5 | $0.00018 | $0.01037 |
| Haiku 4.5 | $0.00009 | $0.00519 |
Grade A, and why
iso-issue-tracking scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 3d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 436 lines — stays where its author put it; the contents beside it link to each section on GitHub.
iso-issue-tracking
Adapters
The board is reached through fourteen tk_* verbs defined in
scripts/adapters/<kind>.sh, selected by tracker.kind in the Iso config.
tracking.sh owns the parts that must not vary — the ledger, redaction, plan
resolution, the transition gates — and never names a vendor.
| kind | adapter |
|---|---|
multica |
adapters/multica.sh — the shipping adapter |
none |
adapters/none.sh — every verb a successful no-op |
An unknown kind falls back to none and logs it, because tracking may never
fail the run that invoked it.
A new adapter defines all fourteen verbs and returns normalised output —
list verbs emit <id>\t<name> lines, not the vendor's JSON — so nothing
downstream has to imitate another board's field names.
scripts/adapters/contract.test.sh is the check.
Redaction stays in tracking.sh, deliberately: an adapter is the file most
likely to be written quickly against an unfamiliar API, and it is the last
place a [redacted] should depend on.
scripts/tracking.sh is called by the Claude Code session hooks for reconcile
and end. The iso-* skills call it at their own boundaries, and you call it
for the work that never went through a plan.
The board answers "what is being worked on and where is it", not "what happened step by step". Every status change corresponds to a point the chain already reaches and already announces; nothing infers intent from a prompt.
| transition | fact that drives it | who writes it |
|---|---|---|
→ todo |
/iso-plan finished writing the plan |
iso-plan |
→ in_progress |
/iso-write resolved its workspace |
iso-write |
→ blocked |
/iso-write halted and wrote its blocked marker |
iso-write |
→ in_review |
/iso-write stamped the plan implemented (uncommitted) |
iso-write |
→ done + retro |
/iso-push landed the PR |
iso-push |
→ done, no retro |
the merge happened outside a session | reconciler |
→ cancelled |
branch gone, gh reachable, opened_by=claude |
reconciler |
What ships with it
6 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 3d ago Changed · +15 lines eb4f6e6f5d1d
- 8d ago First seen · 421 lines · 88 tokens per session scan A 4dd758672492
iso-issue-tracking is a skill published in the GitHub repository IsaiaScope/ai (2 stars, last pushed 4d ago), licensed MIT. It adds 88 tokens to every session and 5,185 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
skill-register-care
Pflege-Skill, der das dreiteilige Skill-Register konsistent hält (code-skill-index-Kataloge, Skill-Index, SKILL-MAP Family-/Routing-Map). Nutze diesen Skill für einen Drift-Check zwischen dem realen Skill-Inventar und dem dokumentierten Register: fehlende oder zu viele Einträge melden, Counts korrigieren, Stand-Datum…
linear-manager
Manage Linear tickets/comments via direct HTTP GraphQL with python3 scripts/linearmanager.py and token env vars only (no Linear MCP). Supports create/read/update/delete tickets and sub-tickets, issue templates, discovery commands (whoami, teams, projects), creating/moving tickets under a project, workflow status…
agent-code-goal-planner
Agent skill for code-goal-planner - invoke with $agent-code-goal-planner.
agent-code-goal-planner
Agent skill for code-goal-planner - invoke with $agent-code-goal-planner.
task-summary
Analyze unstructured content and create structured Linear tickets (single or parent + sub-tickets). Default team CF. Delegates to linear-manager skill.
agent-automation-smart-agent
Agent skill for automation-smart-agent - invoke with $agent-automation-smart-agent.